© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 3162
    Prev
    Next
    INDEX
    Explanations

    terms related to research methodologies and themes in clinical studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by "will"

    np_acts-logits-general · gemini-2.0-flash

    future tense auxiliaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LastError
    -0.54
     isInitialized
    -0.47
     المعيارى
    -0.46
     unknowingly
    -0.46
     sometimes
    -0.46
    migrationBuilder
    -0.45
    mybatisplus
    -0.44
     often
    -0.44
     unwittingly
    -0.44
     الرياضيه
    -0.43
    POSITIVE LOGITS
     will
    1.31
     lesz
    0.86
     saranno
    0.84
     akan
    0.83
     będzie
    0.79
     zullen
    0.79
     serán
    0.78
     sẽ
    0.77
     budou
    0.77
     будет
    0.76
    Activations Density 0.558%

    No Known Activations